© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12094
    Prev
    Next
    INDEX
    Explanations

    instances of the word "error" in code and error messages

    oai_token-act-pair · gemini-2.0-flash

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    error
    -1.58
     error
    -1.52
     errors
    -0.94
    <bos>
    -0.84
    errors
    -0.80
     Error
    -0.71
     errores
    -0.71
     erreur
    -0.70
    erreur
    -0.68
     ошибка
    -0.66
    POSITIVE LOGITS
    IndentedString
    0.90
     &___
    0.75
    tagHelperRunner
    0.75
     ExecuteAsync
    0.71
    saraba
    0.71
    发表于
    0.71
     vuitton
    0.71
    fjspx
    0.69
    AddTagHelper
    0.67
    Ech
    0.67
    Activations Density 0.709%

    No Known Activations